Pillar Security — RedGraph
Knowledge graph of real-world AI attack chains for evidence-based threat modelling.
What it does
A knowledge graph of real-world AI attack chains from Pillar Security. Maps actual attack patterns — not theoretical — enabling evidence-based threat modelling and defence prioritisation for AI systems.
Security relevance
RedGraph provides empirical attack data rather than theoretical risks. By mapping how AI systems are actually attacked in the wild, security teams can prioritise defences based on real-world frequency and impact rather than hypothetical scenarios.
When to use it
Use when building threat models or prioritising security investments for AI systems. The evidence-based approach is particularly valuable for communicating risk to leadership — real attack chains are more compelling than theoretical frameworks.
OWASP coverage
Risks addressed — mapped to both OWASP Top 10 standards. 4 in LLM, 3 in Agentic.
The raw record
What Yuntona stores. Single source of truth — fork it on GitHub.
name: Pillar Security — RedGraph slug: pillar-security-redgraph type: Mixed category: AI Red Teaming url: https://www.pillar.security/redgraph reviewed: 2026-04 added: 2026-04 updated: 2026-04 risks: llm: [LLM01, LLM02, LLM06, LLM07] asi: [ASI01, ASI02, ASI08] complexity: Guided Setup pricing: — audience: Red Team lifecycle: [scope] tags: [Agentic, AppSec, Attack Graph, Platform]